ALMNet: Adjacent Layer Driven Multiscale Features for Salient Object Detection

Gupta, Ashish Kumar; Seal, Ayan; Khanna, Pritee; Krejcar, Ondřej

doi:10.1109/tim.2021.3108503

Cited by 17 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments were conducted to validate the recognition of underwater targets by an improved feature enhancement network method for weak feature target recognition. As for different types of underwater weak feature target images, four sets of simulation experiments are designed in this section to verify the effectiveness of the proposed algorithm and compare it with MR-CNN [22], SLMS-SSD [24], DNTDF [25] and ALMNet [26]. Experiments in this paper have been conducted to recognize several specific classes of target images, and four of them, Torpedo, Submarine, Frogman and AUV, were selected for analysis of recognition accuracy in this paper.…”

Section: Resultsmentioning

confidence: 99%

“…Since reusing feature information leads to unclear weights, Fang [25] proposed a densified, lightweight top-down network structure for effective integration of multi-scale features. Gupta [26] pointed out that the drawback of multi-scale feature methods is mainly that spatial details are ignored until the final fusion stage, so each channel in the aggregated features is weighted according to the adjacent layers to enhance the distinguishing power of the feature representation. In summary, reducing the loss of spatial information while ensuring the acquisition of strong semantic information is the key to improving classification and localization accuracy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

IFE-net: improved feature enhancement network for weak feature target recognition in autonomous underwater vehicles

Cai,

Zhang,

et al. 2024

Robotica

View full text Add to dashboard Cite

The recognizing underwater targets is a crucial component of autonomous underwater vehicle patrols and detection efforts. In the process of visual image recognition in real underwater environment, the spatial and semantic features of the target often appear to different degrees of loss, and the scarcity of specific types of underwater samples leads to unbalanced data on categories. This kind of problem makes the target features appear weak and seriously affects the accuracy of underwater target recognition. Traditional deep learning methods based on data and feature enhancement cannot achieve ideal recognition effect. Based on the above difficulties, this paper proposes an improved feature enhancement network for weak feature target recognition. Firstly, a multi-scale spatial and semantic feature enhancement module is constructed to extract the feature information of the extraction target accurately. Secondly, this paper solves the influence of target feature distortion on classification through multi-scale feature comparison of positive and negative samples. Finally, the Rank & Sort Loss function was used to train the depth target detection to solve the problem of recognition accuracy under highly unbalanced sample data. Experimental results show that the recognition accuracy of the proposed method is 2.28% and 3.84% higher than that of the existing algorithms in the recognition of underwater fuzzy and distorted target images, which demonstrates the effectiveness and superiority of the proposed method.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

IFE-net: improved feature enhancement network for weak feature target recognition in autonomous underwater vehicles

Cai,

Zhang,

et al. 2024

Robotica

View full text Add to dashboard Cite

show abstract

“…For example, Li et al [12] learned multiscale features via CNNs for salient object detection. Gupta et al [16] extracted adjacent-layer features at one resolution for saliency prediction. Wang et al [17] designed a salient object detection architecture via local estimation and global search.…”

Section: A Cnns For Salient Object Detectionmentioning

confidence: 99%

Disentangled Capsule Routing for Fast Part-Object Relational Saliency

Liu

Zhang²,

Liu

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Recently, the Part-Object Relational (POR) saliency underpinned by the Capsule Network (CapsNet) has been demonstrated to be an effective modeling mechanism to improve the saliency detection accuracy. However, it is widely known that the current capsule routing operations have huge computational complexity, which seriously limited the usability of the POR saliency models in real-time applications. To this end, this paper takes an early step towards a fast POR saliency inference by proposing a novel disentangled part-object relational network. Concretely, we disentangle horizontal routing and vertical routing from the original omnidirectional capsule routing, thus generating Disentangled Capsule Routing (DCR). This mechanism enjoys two advantages. On one hand, DCR that disentangles orthogonal 1D (i.e., vertical and horizontal) routing greatly reduces parameters and routing complexity, resulting in much faster inference than omnidirectional 2D routing adopted by existing CapsNets. On the other hand, thanks to the light POR cues explored by DCR, we could conveniently integrate the part-object routing process to different feature layers in CNN, rather than just applying it to the small-scaled one as in previous works. This helps to increase saliency inference accuracy. Compared to previous POR saliency detectors, DPORTNet infers visual saliency (5 ∼ 9) × faster, and is more accurate. DPORTNet is available under the open-source license at https://github.com/liuyi1989/DCR.

show abstract

“…In recent years, tremendous progress has been made in measurement science by applying deep neural networks (DNN) techniques to computer vision applications such as salient object detection [13] , [14] , facial expression recognition [15] , [16] , and deception detection [17] , thus DNN models have become the defacto-standard nowadays. DNN has specialized in learning-rich images with high-level discriminatory semantic characteristics automatically, eliminating the need for hand-crafted descriptors.…”

Section: Introductionmentioning

confidence: 99%